Human motion generation aims to generate natural human pose sequences and shows
immense potential for real-world applications. Substantial progress has been made recently …

Three-dimensional skeleton-based action recognition (3D SAR) has gained important
attention within the computer vision community, owing to the inherent advantages offered by …

Abstract 3D human pose data collected in controlled laboratory settings present challenges
for pose estimators that generalize across diverse scenarios. To address this domain …

The estimation of 3D human motion from video has progressed rapidly but current methods
still have several key limitations. First most methods estimate the human in camera …

While head-mounted devices are becoming more compact they provide egocentric views
with significant self-occlusions of the device user. Hence existing methods often fail to …

In-context learning provides a new perspective for multi-task modeling for vision and NLP.
Under this setting the model can perceive tasks from prompts and accomplish them without …

Recent transformer-based approaches have demonstrated excellent performance in 3D
human pose estimation. However, they have a holistic view and by encoding global …

Abstract Large Language Models (LLMs) have shown remarkable emergent abilities in
unifying almost all (if not every) NLP tasks. In the human motion-related realm however …

Skeleton-based action recognition has attracted lots of research attention. Recently to build
an accurate skeleton-based action recognizer a variety of works have been proposed …

Most existing one-shot skeleton-based action recognition focuses on raw low-level
information (eg., joint location), and may suffer from local information loss and low …